SHELDON1 is the first true hybridization of NLP machine reading and the Semantic Web. It extracts RDF data from text using a machine reader: the extracted RDF graphs are compliant to Semantic Web and Linked Data. It goes further and applies Semantic Web practices and technolo- gies to extend the current human-readable web. The input is represented by a sentence in any language. SHELDON includes different capabilities in order to extend machine reading to Semantic Web data: frame detection, topic ex- traction, named entity recognition, resolution and corefer- ence, terminology extraction, sense tagging and disambigua- tion, taxonomy induction, semantic role labeling, type in- duction, sentiment analysis, citation inference, relation and event extraction, nice visualization tools which make use of the JavaScript infoVis Toolkit and RelFinder. A demo of SHELDON can be seen and used at http://wit.istc.cnr. it/stlab-tools/sheldon.

Extracting knowledge from text using SHELDON, a Semantic Holistic framEwork for LinkeD ONtology data

REFORGIATO RECUPERO, DIEGO ANGELO GAETANO;
2015

Abstract

SHELDON1 is the first true hybridization of NLP machine reading and the Semantic Web. It extracts RDF data from text using a machine reader: the extracted RDF graphs are compliant to Semantic Web and Linked Data. It goes further and applies Semantic Web practices and technolo- gies to extend the current human-readable web. The input is represented by a sentence in any language. SHELDON includes different capabilities in order to extend machine reading to Semantic Web data: frame detection, topic ex- traction, named entity recognition, resolution and corefer- ence, terminology extraction, sense tagging and disambigua- tion, taxonomy induction, semantic role labeling, type in- duction, sentiment analysis, citation inference, relation and event extraction, nice visualization tools which make use of the JavaScript infoVis Toolkit and RelFinder. A demo of SHELDON can be seen and used at http://wit.istc.cnr. it/stlab-tools/sheldon.
File in questo prodotto:
File Dimensione Formato  
reforgiato-recupero-2015-extracting-knowledge-from.pdf

Solo gestori archivio

Tipologia: versione post-print
Dimensione 529.36 kB
Formato Adobe PDF
529.36 kB Adobe PDF   Visualizza/Apri   Richiedi una copia

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: http://hdl.handle.net/11584/141874
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 16
  • ???jsp.display-item.citation.isi??? 7
social impact